Raman spectroscopy analysis combined with computed tomography imaging to identify microsatellite instability in...

Area of Science:

• Biomedical Optics
• Spectroscopy
• Oncology

Background:

• Accurate determination of microsatellite instability (MSI) status is crucial for guiding gastric cancer treatment.
• Current clinical methods for MSI diagnosis are time-consuming, expensive, and experimentally demanding.

Purpose of the Study:

• To develop a novel, efficient, and non-invasive method for classifying gastric cancer MSI status using Raman spectroscopy.
• To address challenges posed by tumor heterogeneity in MSI classification.

Main Methods:

• Development of the Euclidean distance-based Raman Spectroscopy (EDRS) algorithm to establish a standard spectrum for microsatellite stable status.
• Calculation of spectral similarity to assess MSI status.
• Integration of EDRS with computed tomography for a joint classification model.

Main Results:

• The EDRS algorithm achieved a high accuracy of 94.6% in classifying MSI status, outperforming traditional machine learning algorithms.
• The joint EDRS and computed tomography model demonstrated strong performance with an AUC of 0.914 and accuracy of 94.6%.
• The EDRS method effectively mitigates the impact of tumor heterogeneity on spectral signal variations.

Conclusions:

• Raman spectroscopy, particularly using the EDRS algorithm, provides a robust, rapid, and non-invasive tool for gastric cancer MSI status identification.
• This technique offers a promising alternative to existing diagnostic methods, potentially improving clinical workflow and patient treatment strategies.
• The study highlights the potential of Raman spectroscopy in clinical diagnostics and personalized oncology.